Expedite contact center intelligence through our call analytics solution. Built on a serverless analytics platform leveraging Amazon Comprehend and Amazon Transcribe, our solution simplifies and accelerates time to insight on customer calls. Features include sentiment analysis, domain specific transcription and call audio archives, all accessible through an easy-to-use admin portal.
Enhance Customer Experiences in Contact Centers by Gaining Insights Through
AWS Services Leveraged
Amazon Comprehend uses natural language processing (NLP) to extract insights about the content of the call transcripts. It develops insights by recognizing the entities, key phrases, language, sentiments in the transcript.
Amazon Transcribe is a fully managed automatic speech recognition (ASR) service that makes it easy for us to convert audio conversations to text.
AWS Glue is a fully managed ETL (extract, transform, and load) service that makes it simple and cost-effective to categorize data, clean it, enrich it, and move it reliably between various data stores. AWS Glue crawlers automatically infer database and table schema from the text analysis output file and stores the associated metadata in the AWS Glue Data Catalog.
Athena is an interactive query service that makes it easy to analyze data directly in Amazon Simple Storage Service (Amazon S3) using standard SQL. You can use Athena to run ad-hoc queries against the text analysis bucket.
Amazon DynamoDB is a fully managed NoSQL database service that is used in the solution to store the Status of workload throughout.
AWS Lambda allows you to run code without provisioning or managing servers.
AWS CloudFormation enables you to create and provision AWS infrastructure deployments predictably and repeatedly. The entire solution’s infrastructure is built as Code with CloudFormation.
AWS QuickSight is a business analytics service you can use to build visualizations, perform ad hoc analysis, and get business insights from your data. In this solution we use QuickSight to get an aggregated view of the call transcripts insights. We use it to answer questions like “What was the most negative statement uttered by a customer?”
How it Works:
- An S3 bucket that stores contact center audio recordings
- A Lambda function that transcribes the audio recordings to call transcripts
- An S3 bucket that stores the transcripts
- A DynamoDB table that stores audio URI, transcript URI, text analysis URI and job status
- A lambda function that separates turns from the transcript
- An S3 bucket that stores the separated turn transcripts
- A lambda function that analyses the separated transcripts
- An S3 bucket that stores the text analysis output
- A glue crawler that pulls metadata from the text analysis and a glue table
- An Athena Query that fetches turn by turn sentiment and scores
- Amazon API Gateway that exposes provisioning endpoints through HTTPS
- A dashboard integrated with QuickSight